Dr. Viet Pham

Summary

Smart contracts (SC) are transforming how we can enhance automated public services and how the services are executed and controlled in digital ecosystems. Distributed artificial intelligence (DAI) is a new AI paradigm that uses distributed device computing resources to improve data privacy. It is natural to combine SC and DAI to address challenging research issues, including data privacy, security, and network scalability, thus fostering efficient and responsible actions for reliable digital transformation ecosystems in smart cities and novel energy management models. Although promising, there is no high-level reference framework for designing novel SC/DAI-driven solutions and benchmarking testbeds for essential use cases and scaling their implementation internationally. The SHIELD project will offer a new SC/DAI-driven holistic, security, and privacy service architecture and apply it to important use cases in blockchain network ecosystems and smart city/smart energy case studies. SHIELD focuses on public digital services in smart cities using SC/DAI-driven control and operates over edge and global networks. The framework would incorporate robust security measures and privacy-enhancing capabilities in accordance with the sixth-generation (6G) network standards. Exploiting the unique features and research advances on SC/DAI, SHIELD will enable the training, execution, and automated control of e-services with decentralized, contract-based, and secure natures. The framework will enable new models and methods to minimize energy consumption and fraud losses, optimize computing resources and accidental exceptions, and enhance personalization and environmental awareness for micro/macrodigital transformation systems. SHIELD will bring together an international consortium of researchers from the EU and Asia to implement the framework in their lab and testbed facilities. Furthermore, the work carried out in SHIELD will serve as a steppingstone towards large-scale applications, regulations, and governance smart services in 6G with a vision of a new fully digital transformation society.

Funding Agency

Irish Research Council (IRC)

Programme

CHIST-ERA Call 2023

Summary

ENSURE-6G project will develop robust solutions to provide resilient 6G telecommunication infrastructure in the presence of both cyber and physical attacks in 6G networks. The rationale for the ENSURE-6G project is well justified due to the need for advanced and intelligent security and privacy-enhancing mechanisms deployed in practice within current mobile networks and the necessity of novel efficient mechanisms for future networks. ENSURE-6G will have a strong impact on the careers of all participating staff involved. It will equip them with cutting-edge technical and practical knowledge in the security and privacy of 6G technologies. It will create an opportunity to build a strong professional network and bond with industry partners beyond the project"s completion date. The ENSURE-6G will aim to ensure that the EU is at the forefront of security and privacy requirements of 6G networks and that new security measures are designed to mitigate the risks associated with new 6G end-user devices and users.

Funding Agency

European Research Executive Agency

Programme

HORIZON-MSCA-2023-SE-01 (MSCA Staff Exchanges 2023)

Project Type

Research

Summary

Multi-access edge computing (MEC) is a key technology in 5G and beyond, and machine learning is a promising tool for low-complexity, fast-response, and easy-deployment algorithms. A connected vehicle can provide some main functions and services, for example, traffic safety, infotainment, traffic efficiency, cost efficiency, and convenience and interaction. This project aims to utilise machine learning to design optimised resource allocation for 5G with the coexistence of traditional and MEC computing paradigms. From the network and communication perspective, this project will first provide several machine learning-based resource allocation frameworks for connected vehicles with integrated 4C communication, computing, caching, and control. However, a critical concern with conventional machine learning is data privacy since most vehicles want to keep track of their local data and are unwilling to share local data with a third party. To tackle data privacy challenges, this project will utilise federated learning, a new distributed AI concept, for secure computation offloading, caching, and communication in connected vehicle networks. This project further sets on implementing the testbeds to provide more practical and implementation aspects that theoretical results cannot provide.

Funding Agency

Korea NRF

Programme

NRF Basic Science and Research

Project Type

Research

Summary

This project brings together the research area of computer vision, deep learning, and edge computing for interdisciplinary collaboration. While in recent years, there has been a great deal of interest from scientists and researchers in these areas, there has been little work on the design and development of an intelligent surveillance system that integrates cutting-edge technologies for efficient activity recognition. More specifically, the contributions of this project can be stated as (1) A HAR framework is developed by fully exploiting the benefits of human skeleton information (i.e., privacy protection and latency reduction) in IoT environments, (2) A comprehensive study of feature extraction schemes is provided to investigate the effectiveness and ability of different feature types in capturing dynamics of body joints in both spatial and temporal domains, (3) Depending on the type of skeletal features, we design various lightweight DL models for inferring human activities on resourced-constrained devices in two directions: CNNs for learning fixed-size video representation and deep sequential networks (RNN and Transformer) for learning dynamics of variable-length sequences, and (4) We propose a collaborative computation offloading algorithm to achieve the load balancing among the edge servers and to meet latency and accuracy requirements of an edge HAR system. Hence, the project has both high scientific and commercial potential due to the high demand for large-scale surveillance applications for industry, healthcare, risk monitoring, and automated assisted living systems.

Funding Agency

Nazarbayev University

Programme

FDCRGP Grant

Project Type

Research